Machine learning models for predicting the risk of depressive symptoms in Chinese college students

IntroductionDepression is highly prevalent among college students, and accurately identifying risk factors is essential for timely intervention. Given the limitations of traditional linear models in managing high-dimensional data, this study employed machine learning techniques to predict depressive...

Full description

Saved in:
Bibliographic Details
Main Authors: Chengfu Yu, Xiangxuan Kong, Weijie Yu, Xingcan Ni, Jing Chen, Xiaoyan Liao
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-08-01
Series:Frontiers in Psychiatry
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fpsyt.2025.1648585/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849771768975196160
author Chengfu Yu
Xiangxuan Kong
Weijie Yu
Xingcan Ni
Jing Chen
Xiaoyan Liao
author_facet Chengfu Yu
Xiangxuan Kong
Weijie Yu
Xingcan Ni
Jing Chen
Xiaoyan Liao
author_sort Chengfu Yu
collection DOAJ
description IntroductionDepression is highly prevalent among college students, and accurately identifying risk factors is essential for timely intervention. Given the limitations of traditional linear models in managing high-dimensional data, this study employed machine learning techniques to predict depressive symptoms.MethodData were collected from 1,635 Chinese college students and included 38 sociodemographic, psychological, and social variables. Four machine- learning algorithms, Random Forest, XGBoost, LightGBM, and Support Vector Machine, were evaluated.ResultsResults showed that the Random Forest model achieved the highest discriminant performance with an AUC of 0.87 and an accuracy of 0.79, and identified key predictors such as sleep disturbance, perceived stress, experiential avoidance, and self-criticism. SHapley Additive exPlanations analysis further revealed that deteriorating sleep quality and heightened stress levels significantly increased the risk of depressive symptoms.DiscussionThese findings validate the effectiveness of Random Forest in capturing complex data interactions and offer actionable insights for targeted mental health interventions. Future studies should improve generalizability by incorporating more diverse samples and physiological biomarkers.
format Article
id doaj-art-9e7b558ba5fa4119bf3289d59776d9bb
institution DOAJ
issn 1664-0640
language English
publishDate 2025-08-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Psychiatry
spelling doaj-art-9e7b558ba5fa4119bf3289d59776d9bb2025-08-20T03:02:30ZengFrontiers Media S.A.Frontiers in Psychiatry1664-06402025-08-011610.3389/fpsyt.2025.16485851648585Machine learning models for predicting the risk of depressive symptoms in Chinese college studentsChengfu Yu0Xiangxuan Kong1Weijie Yu2Xingcan Ni3Jing Chen4Xiaoyan Liao5Department of Psychology/Research Center of Adolescent Psychology and Behavior, School of Education, Guangzhou University, Guangzhou, Guangdong, ChinaDepartment of Psychology/Research Center of Adolescent Psychology and Behavior, School of Education, Guangzhou University, Guangzhou, Guangdong, ChinaDepartment of Psychology/Research Center of Adolescent Psychology and Behavior, School of Education, Guangzhou University, Guangzhou, Guangdong, ChinaDepartment of Psychology/Research Center of Adolescent Psychology and Behavior, School of Education, Guangzhou University, Guangzhou, Guangdong, ChinaDepartment of Psychology/Research Center of Adolescent Psychology and Behavior, School of Education, Guangzhou University, Guangzhou, Guangdong, ChinaSchool of Psychology, South China Normal University, Guangzhou, Guangdong, ChinaIntroductionDepression is highly prevalent among college students, and accurately identifying risk factors is essential for timely intervention. Given the limitations of traditional linear models in managing high-dimensional data, this study employed machine learning techniques to predict depressive symptoms.MethodData were collected from 1,635 Chinese college students and included 38 sociodemographic, psychological, and social variables. Four machine- learning algorithms, Random Forest, XGBoost, LightGBM, and Support Vector Machine, were evaluated.ResultsResults showed that the Random Forest model achieved the highest discriminant performance with an AUC of 0.87 and an accuracy of 0.79, and identified key predictors such as sleep disturbance, perceived stress, experiential avoidance, and self-criticism. SHapley Additive exPlanations analysis further revealed that deteriorating sleep quality and heightened stress levels significantly increased the risk of depressive symptoms.DiscussionThese findings validate the effectiveness of Random Forest in capturing complex data interactions and offer actionable insights for targeted mental health interventions. Future studies should improve generalizability by incorporating more diverse samples and physiological biomarkers.https://www.frontiersin.org/articles/10.3389/fpsyt.2025.1648585/fullmachine learningdepressive symptomsrisk and protective factorscollege studentsrandom forest
spellingShingle Chengfu Yu
Xiangxuan Kong
Weijie Yu
Xingcan Ni
Jing Chen
Xiaoyan Liao
Machine learning models for predicting the risk of depressive symptoms in Chinese college students
Frontiers in Psychiatry
machine learning
depressive symptoms
risk and protective factors
college students
random forest
title Machine learning models for predicting the risk of depressive symptoms in Chinese college students
title_full Machine learning models for predicting the risk of depressive symptoms in Chinese college students
title_fullStr Machine learning models for predicting the risk of depressive symptoms in Chinese college students
title_full_unstemmed Machine learning models for predicting the risk of depressive symptoms in Chinese college students
title_short Machine learning models for predicting the risk of depressive symptoms in Chinese college students
title_sort machine learning models for predicting the risk of depressive symptoms in chinese college students
topic machine learning
depressive symptoms
risk and protective factors
college students
random forest
url https://www.frontiersin.org/articles/10.3389/fpsyt.2025.1648585/full
work_keys_str_mv AT chengfuyu machinelearningmodelsforpredictingtheriskofdepressivesymptomsinchinesecollegestudents
AT xiangxuankong machinelearningmodelsforpredictingtheriskofdepressivesymptomsinchinesecollegestudents
AT weijieyu machinelearningmodelsforpredictingtheriskofdepressivesymptomsinchinesecollegestudents
AT xingcanni machinelearningmodelsforpredictingtheriskofdepressivesymptomsinchinesecollegestudents
AT jingchen machinelearningmodelsforpredictingtheriskofdepressivesymptomsinchinesecollegestudents
AT xiaoyanliao machinelearningmodelsforpredictingtheriskofdepressivesymptomsinchinesecollegestudents